Industrial Technology Research Institute

Candor Ltd.

Wen-Pin Hsu

Wei-Cheng Wang

Chien-Chih Huang

Cheng-Han Wu

Ming-Chun Hsyu

Chun-Te Yu

Ting-Hui Kao

Chi-Kang Chen

Chih-Hao Hsu

Chao-Hung Chen

Hsuan-Hung Liu

Jen-How Wang

A data processing method used in neural network computing is provided. During a training phase of a neural network model, a feedforward procedure based on a calibration data is performed to obtain distribution information of a feedforward result for at least one layer of the neural network model. During the training phase of the neural network model, a bit upper bound of a partial sum is generated based on the distribution information of the feedforward result. During an inference phase of the neural network model, a bit-number reducing process is performed on an original operation result of an input data and a weight for the neural network model according to the bit upper bound of the partial sum to obtain an adjusted operation result.

Data processing method and device for bit-number reduction in a neural network by establishing bit upper bound and bit lower bound using distribution information

A network service method includes the following steps. A multi-access edge computing cloud server receives a service request from a terminal device and records the internal Internet protocol address of the terminal device. And, the internal Internet protocol address transmitted from the terminal device or the multi-access edge computing cloud server is received by a core cloud server, and correspondence between the internal Internet protocol address and the external Internet protocol address of the terminal device is recorded by the core cloud server.

Network service system and network service method

A network service method includes: a core cloud server returns all running service identification information; a multi-access edge computing cloud server receives a service request from a terminal device; and the multi-access edge computing cloud server determines whether an application that corresponds to the service request exists in the multi-access edge computing cloud server, according to the service identification information reported by the core cloud server; after the multi-access edge computing cloud server integrates the current state with the application being run by the multi-access edge computing cloud server, the terminal device is directed to the multi-access edge computing cloud server, and the multi-access edge computing cloud server provides the application to the terminal device.

A digital dental mesh segmentation method and a digital dental mesh segmentation device are provided. The digital dental mesh segmentation method includes: receiving a digital dental mesh, including a plurality of teeth; inserting a tooth interface separator at a tooth interface of the digital dental mesh, the tooth interface separator being at a first location; receiving a three-dimensional movement signal and a three-dimensional rotation signal to move and rotate the tooth interface separator from the first location to a second location; and segmenting the digital dental mesh according to the tooth interface separator at the second location to obtain an independent digital teeth model.

Digital dental mesh segmentation method and digital dental mesh segmentation device

Growing community of inventors

Taipei, Taiwan

Wen-Pin Hsu